JP2023084166A - Drainage pump device, drainage pump management system, drainage pump support plan creation device, inference device, machine learning device, drainage pump support plan creation method, inference method, and machine learning method - Google Patents

Abstract

To provide a drainage pump device which can reduce the flooding damage at a monitoring point.SOLUTION: A drainage pump device 2 comprises: a water level detection part 24 for detecting a water level at a monitoring point; a pump part 25 for draining water which is accumulated at the monitoring point; and a pump control part 20 for controlling an operation of the pump part 25 on the basis of the water level which is detected by the water level detection part 24. The drainage pump device further comprises: a weather information acquisition part 201 for acquiring the weather information at the monitoring point; an abnormality determination part 202 for determining whether or not an abnormality occurs in the water level detection part 24 or the pump part 25; a water level detection part abnormality processing part 203 for controlling the operation of the pump part 25 on the basis of the weather information when it is determined that the abnormality occurs in the water level detection part 24; and a pump part abnormality processing part 204 for outputting support requirement information for requiring the support of drainage work by a drainage pump vehicle and a worker on the basis of at least one of the water level detected by the water level detection part 24 and the weather information, when it is determined that the abnormality occurs in the pump part 25.SELECTED DRAWING: Figure 2

Description

The present invention provides a drainage pump device, a drainage pump management system, a drainage pump support plan creation device,
The present invention relates to an inference device, a machine learning device, a drainage pump support plan creation method, an inference method, and a machine learning method.

Facilities such as buildings, underground parking lots, underground malls, underpasses, and underpasses are equipped with drainage pump devices to prevent flood damage when torrential rain occurs. The drainage pump device starts operation of the drainage pump when the water level at the monitoring point reaches a predetermined operating water level.
It is intended to prevent flood damage (see, for example, Patent Literature 1 and Patent Literature 2).

JP-A-2002-235450 JP-A-6-116972

The drainage pump devices disclosed in Patent Documents 1 and 2 are operated only when the water level at the monitored location reaches a predetermined operating water level due to torrential rain or the like, so the frequency of operation of the drainage pump is relatively high. do not have. For this reason, regular inspections are conducted to check whether there is any abnormality in the drainage pump equipment. It may not work properly. In addition, if the drainage pump device does not operate normally, there is a high risk that the facility in which the drainage pump device is installed will be submerged, and flood damage could not be properly prevented.

In view of the above-described problems, the present invention provides a drainage pump device, a drainage pump management system, a drainage pump support plan creation device, an inference device, a machine learning device, and a drainage pump support plan that can reduce flood damage at monitored locations. The object is to provide a creation method, an inference method, and a machine learning method.

In order to achieve the above object, a drainage pump device according to one aspect of the present invention includes:
a water level detection unit that detects the water level at the monitoring location;
a pump unit for draining water accumulated in the monitoring location;
A drainage pump device comprising: a pump control section that controls operation of the pump section based on the water level detected by the water level detection section,
The pump control unit
a weather information acquisition unit that acquires weather information of the monitoring location;
an abnormality determination unit that determines whether an abnormality has occurred in the water level detection unit or the pump unit;
a water level detection unit abnormality processing unit that controls the operation of the pump unit based on the weather information when it is determined that an abnormality has occurred in the water level detection unit;
When it is determined that an abnormality has occurred in the pump unit, at least one of the water level detected by the water level detection unit and the weather information is used to request support for drainage work by at least one of a drainage pump vehicle and a worker. and a pump unit abnormality processing unit for outputting support request information.

According to the drainage pump device according to one aspect of the present invention, the pump control section determines whether or not an abnormality has occurred in the water level detection section or the pump section, and when it is determined that an abnormality has occurred in the water level detection section controls the operation of the pump unit based on the weather information of the monitoring point, and when it is determined that an abnormality has occurred in the pump unit, at least one of the water level detected by the water level detection unit and the weather information of the monitoring point Since the support request information is output based on the above information, even if an abnormality occurs in the water level detection unit or the pump unit, it is possible to reduce flood damage at the monitored location.

Problems, configurations, and effects other than the above will be clarified in the mode for carrying out the invention, which will be described later.

BRIEF DESCRIPTION OF THE DRAWINGS It is a whole block diagram which shows an example of the drainage pump management system 1 which concerns on 1st Embodiment. 1 is a block diagram showing an example of a drainage pump device 2 according to a first embodiment; FIG. It is a block diagram showing an example of management device 3 concerning a 1st embodiment. 3 is a hardware configuration diagram showing an example of a computer 900; FIG. 4 is a flow chart showing an example of the operation of the drainage pump device 2 according to the first embodiment; 4 is a flow chart showing an example of the operation of the management device 3 according to the first embodiment; It is a whole block diagram which shows an example of the drainage pump management system 1a which concerns on 2nd Embodiment. It is a block diagram which shows an example of the drainage pump apparatus 2a which concerns on 2nd Embodiment. It is a block diagram which shows an example of the machine-learning apparatus 8 which concerns on 2nd Embodiment. 1 is a diagram showing an example of a learning model 12 and learning data 11; FIG. It is a block diagram which shows an example of the management apparatus 3a which concerns on 2nd Embodiment. FIG. 11 is a functional explanatory diagram showing an example of a management device 3a according to the second embodiment; 9 is a flow chart showing an example of the operation of the machine learning device 8 according to the second embodiment; It is a flow chart which shows an example of operation of controlling device 3a concerning a 2nd embodiment.

Embodiments for carrying out the present invention will be described below with reference to the drawings. Below,
The scope necessary for the description to achieve the object of the present invention is schematically shown, and the scope necessary for the description of the relevant portion of the present invention is mainly described. and

(First embodiment)
FIG. 1 is an overall configuration diagram showing an example of a drainage pump management system 1 according to the first embodiment. The drainage pump management system 1 includes, as its main components, one or a plurality of drainage pump devices 2, a management device 3 capable of communicating with the drainage pump device 2, and a manager 10 of the drainage pump device 2.
A manager terminal device 4 used by 0, a drainage pump vehicle 5 used to support drainage work when an abnormality occurs in the drainage pump device 2, and a worker terminal device 6 used by a worker 101 who supports the drainage work. and a weather information providing device 7 for providing weather information.

Each component of the drainage pump management system 1 is configured by, for example, a general-purpose or dedicated computer (see FIG. 4 described later), and is connected to a network 10 so that various types of data can be exchanged with each other. . The number of components of the drainage pump management system 1 and the connection configuration of the network 10 are not limited to the example shown in FIG. 1, and may be changed as appropriate. Moreover, the drainage pump management system 1 may omit some of the above components, and in that case, cooperate with an external system or substitute an external system.

The drainage pump device 2 is installed, for example, in facilities such as a basement, a building having a drainage tank, a drainage pit, etc., an underground parking lot, an underground mall, an underground passage, an underpass, and the like. The drainage pump device 2 automatically starts operation when the water level at the monitoring point of these facilities reaches a predetermined operating water level, and discharges the water accumulated at the monitoring point to the outside (for example, rainwater pipes, sewage pipes, rivers, etc.). Drain. In addition, the drainage pump device 2 has an abnormality determination function that determines whether or not an abnormality has occurred in each part of the device, and when an abnormality that makes it impossible to operate occurs, at least one of the drainage pump vehicle 5 and the worker 101 Assistance request information requesting assistance for drainage work is output (transmitted) to the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, etc. via the management device 3, for example.

In order to complement the abnormality determination function of the drainage pump device 2, the management device 3 determines whether or not an abnormality has occurred in the drainage pump device 2 by a method different from the abnormality determination function of the drainage pump device 2. It has soundness judgment function. In addition, when an abnormality occurs in the drainage pump device 2, the management device 3 outputs (transmits) support request information to, for example, the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the like.

The administrator terminal device 4 is composed of, for example, a stationary computer or a portable computer,
Used by administrator 100 . The administrator terminal device 4 is installed with programs such as applications and browsers, receives various input operations, and receives various information (for example, the operation status of the drainage pump device 2, the abnormality determination function, etc.) via the display screen and voice. and judgment results by the soundness judgment function, support request information, etc.).

The drainage pump vehicle 5 is a vehicle that functions as a mobile or portable drainage pump, with a generator, a submersible pump, a control panel, an operation display panel, a hose, a cable, and the like loaded on the carrier. The drainage pump vehicle 5 is moved to the site (monitored location of the drainage pump device 2) requested by the worker 101 for assistance in the drainage work, and the drainage work is performed by installing the submersible pump.

The worker terminal device 6 is composed of, for example, a stationary computer or a portable computer,
Used by worker 101 . Like the manager terminal device 4, the worker terminal device 6 is installed with programs such as applications and browsers, receives various input operations, and receives various information (for example, support request information, etc.). In addition, the worker terminal device 6 may be composed of an in-vehicle device such as a car navigation device mounted on the drainage pump vehicle 5 .

The weather information providing device 7 provides, as weather information, actual weather data at the current time or past time, and weather forecast data at a future time (for example, 1 hour, 2 hours, etc.) after the current time. do. The weather information includes, for example, weather elements such as the amount of precipitation and the weather for each area divided into meshes of a predetermined size. The method of providing weather information may be either a pull type or a push type, and the date and time, period, time interval, area, etc. to be provided may be specified. Note that the weather information providing device 7 may be composed of an external device managed by, for example, the Japan Meteorological Agency or a weather information providing company.

The network 10 transmits and receives data by wired communication, wireless communication, or a combination of wired and wireless communication according to any communication standard. Specifically, for example, a standardized communication network such as the Internet, a communication network managed in a building such as a local network, or a combination of these communication networks can be used. As a communication standard for wireless communication, an international standard is typically used. IEEE8 as an international standard communication means
02.15.4, IEEE802.15.1, IEEE802.15.11a, 11b,
11g, 11n, 11ac, 11ad, ISO/IEC14513-3-10, IEEE
There are methods such as 802.15.4g. In addition, Bluetooth (registered trademark), Blue
tooth Low Energy, Wi-Fi, ZigBee®, Sub-GH
Communication standards such as Z, EnOcean (registered trademark), and LTE may also be used.

(Drain pump device 2)
FIG. 2 is a block diagram showing an example of the drainage pump device 2 according to the first embodiment. The drainage pump device 2 includes a pump control unit 20 configured by a processor or the like, an HDD (Hard
Disk Drive), SSD (Solid State Drive), memory, etc., a storage unit 21; a communication unit 22, which is a communication interface with the network 10; , a water level detection unit 24 that detects the water level at the monitoring location, and a pump unit 25 that drains the water accumulated at the monitoring location.
and

The water level detection unit 24 is composed of a water level sensor, a sensor detection circuit, and the like for detecting the water level at the monitored location. The water level sensor may be, for example, a level sensor that detects the water level at the monitoring location step by step or continuously, or a level switch that detects whether the water level at the monitoring location has reached a predetermined operating water level. may be configured.

The pump unit 25 includes a motor that rotates an impeller, a motor drive circuit that supplies drive power to the motor, an electromagnetic contactor provided between the motor drive circuit and a power supply, and the like. Pump part 2
5 is composed of, for example, an axial flow pump, a mixed flow pump, a spiral mixed flow pump, etc., but the type of pump is not limited to these examples. The power source of the pump unit 25 may be commercial power or a generator using an engine as a power source, or may use an engine as a power source to rotate an impeller.

Further, the pump unit 25 is configured to be able to receive a pump operation signal instructing the operation of the pump unit 25 from the management device 3 without going through the pump control unit 20 . When the pump unit 25 receives the pump operation signal, the operation of the pump unit 25 is forcibly started regardless of the state of control by the pump control unit 20 and whether or not the detected water level has reached the operating water level.

The storage unit 21 stores drainage pump setting data 210 and a drainage pump control program 211.
and stores an operating system, other programs, various data, and the like. The drainage pump setting data 210 includes information that can be edited by the administrator 100 and the worker 101, such as geographic information indicating the position coordinates (latitude, longitude, and altitude) of the monitored location of the device itself, and the output destination of the support request information. etc. are registered.

By executing the drainage pump control program 211 stored in the storage unit 21, the pump control unit 20 operates a pump operation processing unit 200, a weather information acquisition unit 201, an abnormality determination unit 202,
It functions as a water level detection section abnormality processing section 203 , a pump section abnormality processing section 204 , and a soundness signal transmission processing section 205 .

The pump operation processing unit 200 controls the operation of the pump unit 25 based on the water level detected by the water level detection unit 24 (hereinafter referred to as "detected water level"). The pump operation processing unit 200, for example, determines whether or not the detected water level has reached a predetermined operating water level, and starts operating the pump unit 25 when the detected water level has reached the operating water level. Note that when the operation display unit 23 receives an operation instructing the operation of the pump unit 25, the pump operation processing unit 200 controls the operation of the pump unit 25 regardless of whether or not the detected water level reaches the operating water level. start driving. Further, the pump operation processing unit 200 stops the operation of the pump unit 25 when, for example, the detected water level drops to a predetermined stop water level, or when the operation display unit 23 receives an operation instructing to stop the operation. .

The weather information acquisition unit 201 acquires weather information of the monitored location of the own device. Weather information acquisition unit 2
01 receives weather information from the weather information providing device 7 via the communication unit 22 and the network 10 based on the position coordinates of the monitored location of the device itself registered in the drainage pump setting data 210, for example. Acquire the weather information of the monitoring point of the device.

The abnormality determination unit 202 determines whether or not an abnormality has occurred in the water level detection unit 24 or the pump unit 25 . The abnormality determination unit 202 uses, for example, a normally-on type (normally closed) water level sensor that is turned on when the water level at the monitoring location does not reach the operating water level, and determines the water level at the monitoring location from the weather information at the monitoring location. In a situation where it is judged that there is no or a low possibility of reaching the operating water level (such as a situation where the precipitation amount is "0 mm" for a predetermined period of time), if the detected value of the water level sensor is off, It is determined that an abnormality has occurred in the water level detection unit 24 . Abnormality of the water level detection unit 24 includes disconnection of the water level sensor, failure of the sensor detection circuit, and the like. Further, the abnormality determination unit 202 performs a test operation of the pump unit 25 in the same situation, and when various sensors provided in the motor and the motor drive circuit detect malfunction, an abnormality occurs in the pump unit 25. It is determined that Abnormalities in the pump unit 25 include motor failure, motor drive circuit failure,
Malfunction of an electromagnetic contactor, etc. can be mentioned.

When it is determined that an abnormality has occurred in the water level detection unit 24, the water level detection unit abnormality processing unit 203 controls the operation of the pump unit 25 based on the weather information of the monitored location. Specifically, the water level detection unit abnormality processing unit 203 determines from the weather information of the monitoring location that there is a high possibility that the water level at the monitoring location will reach the operating water level. If the condition continues for a predetermined period, etc., the operation of the pump unit 25 is started.

When determining that an abnormality has occurred in the pump unit 25, the pump unit abnormality processing unit 204 detects at least one of the water level detected by the water level detection unit 24 and the weather information of the monitored location. Support request information requesting support for the drainage work by one side is output to the output destination registered in the drainage pump setting data 210 . Specifically, the pump unit abnormality processing unit 204 outputs support request information when the detected water level reaches the operating water level (a support request water level lower than the operating water level may be used instead of the operating water level). In addition, the pump unit abnormality processing unit 2
04 outputs support request information when it judges from the weather information of the monitoring location that the water level at the monitoring location is highly likely to reach the operating water level.

The output destination of the support request information is the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the like. It may be limited to the drainage pump vehicle 5 and the worker terminal device 6 located in . Further, the support request information may be directly output to the administrator terminal device 4 or the like, or may be output to the administrator terminal device 4 or the like via the management device 3 .

The soundness signal transmission processing unit 205 transmits a soundness signal indicating the soundness of the drainage pump device 2 to the management device 3 via the communication unit 22 and the network 10 according to predetermined soundness transmission conditions. The health condition transmission condition defines a condition for transmitting the health signal, for example, a predetermined transmission period or transmission time.

(Management device 3)
FIG. 3 is a block diagram showing an example of the management device 3 according to the first embodiment. Management device 3
is a management control unit 30 composed of a processor or the like, a storage unit 31 composed of an HDD, an SSD, a memory, etc., and a communication unit 32 which is a communication interface with the network 10.
, an input unit 33 configured by a keyboard, a mouse, etc., and a display unit 34 configured by a display or the like. Note that the input unit 33 and the display unit 34 may be omitted.

The storage unit 31 stores a drainage pump management database 310 and a drainage pump management program 311, as well as an operating system, other programs, various data, and the like. In the drainage pump management database 310, as information that can be edited by the administrator 100, for example, for each drainage pump device 2 to be managed by the management device 3, geographic coordinates (latitude, longitude, altitude) of monitoring locations are stored. Information, output destination of support request information, etc. are registered.

By executing the drainage pump management program 311 stored in the storage unit 31, the management control unit 30 performs a weather information acquisition unit 300, a soundness determination unit 301, a first pump control unit abnormality processing unit 302, and a 2 function as the pump control unit abnormality processing unit 303 .

The weather information acquisition unit 300 acquires weather information of a monitored location in the drainage pump device 2 to be managed. The weather information acquisition unit 300 acquires weather information from the weather information providing device 7 via the communication unit 32 and the network 10, for example, based on the position coordinates of the monitored location of the drainage pump device 2 registered in the drainage pump management database 310. By receiving, the drainage pump device 2
obtains weather information for the monitored location. At this time, if there are a plurality of drainage pump devices 2 to be managed, the weather information acquiring unit 300 acquires weather information on the monitored location of each drainage pump device 2 .

The soundness determination unit 301 determines whether or not an abnormality has occurred in the pump control unit 20 of the drainage pump device 2 according to whether or not the soundness signal has been received from the drainage pump device 2 according to the soundness transmission conditions. do. If the soundness determination unit 301 does not receive the soundness signal from the drainage pump device 2 at the transmission period or the transmission time specified as the soundness transmission condition, the soundness determination unit 301 performs the pump control that is the transmission source of the soundness signal. It is determined that an abnormality has occurred in the unit 20 . At this time, if there are a plurality of drainage pump devices 2 to be managed, the soundness determination unit 301 determines whether or not each drainage pump device 2 has received a soundness signal from each drainage pump device 2. It is determined whether or not an abnormality has occurred in each of the pump control units 20 . An abnormality of the pump control unit 20 includes a failure of a processor or the like that constitutes the pump control unit 20 .

When the first pump control unit abnormality processing unit 302 determines that an abnormality has occurred in the pump control unit 20, based on the weather information of the monitored location of the drainage pump device 2 including the pump control unit 20, the drainage pump Support request information requesting support for the drainage work for the device 2 is output to the output destination registered in the drainage pump management database 310 . Specifically, the first pump control unit abnormality processing unit 302 determines that the water level at the monitoring location is equal to the operating water level based on the weather information for the monitoring location of the drainage pump device 2 where it is determined that the pump control unit 20 has an abnormality. When it is determined that the possibility of reaching the water level is high, the support request information for the drainage pump device 2 is output.

The output destination of the support request information is the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the like. It may be limited to the drainage pump vehicle 5 and the worker terminal device 6 located in . Further, the support request information may be directly output to the administrator terminal device 4 or the like, or may be output to the administrator terminal device 4 or the like via the management device 3 .

When the second pump control unit abnormality processing unit 303 determines that an abnormality has occurred in the pump control unit 20, based on the weather information of the monitored location of the drainage pump device 2 including the pump control unit 20, the drainage pump A pump operation signal instructing the operation of the pump unit 25 of the device 2 is transmitted to the pump unit 25 . Specifically, the second pump control unit abnormality processing unit 303 determines that the water level at the monitoring location is equal to the operating water level based on the weather information at the monitoring location of the drainage pump device 2 where it is determined that the pump control unit 20 has an abnormality. When it is determined that the possibility of reaching the water level is high, a pump operation signal is transmitted to the pump section 25 of the drainage pump device 2 . The operation of the pump unit 25 is started when the pump operation signal is received by the pump unit 25 without going through the pump control unit 20 .

(Hardware configuration of each device)
FIG. 4 is a hardware configuration diagram showing an example of the computer 900. As shown in FIG. Each of the drainage pump device 2, the management device 3, the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the weather information providing device 7 is configured by a general-purpose or dedicated computer 900. FIG.

Computer 900, as shown in FIG. 4, has as its main components a bus 910,
Processor 912, memory 914, input device 916, output device 917, display device 918, storage device 920, communication I/F (interface) section 922, external device I/F section 924, I/O (input/output) device I/ An F unit 926 and a media input/output unit 928 are provided. Note that the above components may be omitted as appropriate depending on the application for which the computer 900 is used.

Processor 912 may include one or more processing units (CPUs (Central Pro
processing unit), MPU (Micro-processing unit)
, DSP (digital signal processor), GPU (Graph
ics processing unit), etc.), and operates as a control unit that controls the entire computer 900 . The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (DRAM, SRAM, etc.) functioning as a main memory, a non-volatile memory (ROM), a flash memory, and the like.

The input device 916 is composed of, for example, a keyboard, mouse, numeric keypad, electronic pen, etc., and functions as an input unit. The output device 917 is configured by, for example, a sound (voice) output device, a vibration device, or the like, and functions as an output unit. A display device 918 is configured by, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, or the like, and functions as an output unit. The input device 916 and the display device 918 may be configured integrally like a touch panel display. The storage device 920 is composed of, for example, an HDD, SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and programs 930 .

The communication I/F unit 922 is connected to a network 940 (which may be the same as the network 10 in FIG. 1) such as the Internet or an intranet by wire or wirelessly, and exchanges data with other computers according to a predetermined communication standard. functions as a communication unit that transmits and receives
An external device I/F unit 924 connects to external devices 9 such as cameras, printers, scanners, and reader/writers.
50 by wire or wirelessly, and functions as a communication unit that transmits and receives data to and from the external device 950 according to a predetermined communication standard. The I/O device I/F unit 926 is connected to I/O devices 960 such as various sensors and actuators, and exchanges with the I/O devices 960, for example, detection signals from sensors and control signals to actuators. functions as a communication unit that transmits and receives various signals and data. The media input/output unit 928, for example,
It is composed of a drive device such as a drive and a CD drive, and reads and writes data with respect to media (non-temporary storage media) 970 such as DVDs and CDs.

In the computer 900 having the above configuration, the processor 912 calls the program 930 stored in the storage device 920 to the memory 914 and executes it, and controls each part of the computer 900 via the bus 910 . Note that the program 930 may be stored in the memory 914 instead of the storage device 920 . The program 930 may be recorded on the media 970 in an installable file format or executable file format and provided to the computer 900 via the media input/output unit 928 . program 93
0 may be provided to computer 900 by downloading via network 940 via communication I/F section 922 . The computer 900 also includes the processor 9
12 executes the program 930 to implement various functions, for example, FPGA, A
It may be realized by hardware such as SIC.

The computer 900 is, for example, a stationary computer or a portable computer, and is an arbitrary form of electronic equipment. The computer 900 may be a client-type computer, a server-type computer, or a cloud-type computer. computer 90
0 may also apply to other devices.

(Operation of drainage pump management system 1)
The operation of the drainage pump management system 1 having the above configuration will be described.

FIG. 5 is a flow chart showing an example of the operation of the drainage pump device 2 according to the first embodiment. An operation example in which the drainage pump device 2 is installed at a monitoring location and the water level at the monitoring location is being monitored by the water level detector 24 will be described below. A series of processes shown in FIG. 5 are repeatedly executed by the drainage pump device 2 at a predetermined cycle.

First, in step S<b>100 , the health signal transmission processing unit 205 transmits a health signal to the management device 3 when it determines that predetermined health transmission conditions (transmission cycle, transmission time, etc.) are satisfied.

Next, in S<b>110 , the weather information acquisition unit 201 acquires the weather information of the monitored location of the own device from the weather information providing device 7 .

Next, in S<b>120 , the abnormality determination section 202 determines whether or not an abnormality has occurred in the water level detection section 24 and whether or not an abnormality has occurred in the pump section 25 .

When it is determined that an abnormality has occurred in the water level detection unit 24 as the determination result of step S120 (step S121: Yes), in step S130, the water level detection unit abnormality processing unit 203 detects the monitoring location acquired in step S120. Based on the weather information of the pump unit 2
It controls the operation of 5.

As a result of the determination in step S120, if it is determined that an abnormality has occurred in the pump unit 25 (step S122: Yes), in step S140, the pump unit abnormality processing unit 204 determines that the water level detected by the water level detection unit 24 is operating. When the water level is reached or step S120
If it is determined that there is a high possibility that the water level at the monitoring location will reach the operating water level based on the weather information for the monitoring location acquired in step 1, support request information is output.

If it is determined that the water level detection unit 24 and the pump unit 25 are not abnormal as a result of determination in step S120 (step S121: No, step S122: No)
In step S<b>150 , the pump operation processing section 200 controls the operation of the pump section 25 based on the water level detected by the water level detection section 24 . In the series of processes (drainage pump control method) shown in FIG. 5, step S100 is a soundness signal transmission process, S110 is a weather information acquisition process, S120 is an abnormality determination process, and step S130 is a water level detection unit abnormality processing process. S140 corresponds to a pump unit abnormality processing step, and step S150 corresponds to a pump operation processing step.

As described above, according to the drainage pump device 2 according to the present embodiment, the pump control unit 20 determines whether or not an abnormality has occurred in the water level detection unit 24 or the pump unit 25, and determines whether the water level detection unit 24 has an abnormality. When it is determined that an abnormality has occurred, the operation of the pump unit 25 is controlled based on the weather information of the monitoring location, and when it is determined that an abnormality has occurred in the pump unit 25, the water level detection unit 24 detects Support request information is output based on at least one of the water level and weather information of the monitoring location.
Therefore, even if an abnormality occurs in the water level detection unit 24 or the pump unit 25, it is possible to reduce flood damage to the monitoring location.

FIG. 6 is a flow chart showing an example of the operation of the management device 3 according to the first embodiment.
A series of processes shown in FIG. 6 are repeatedly executed by the management device 3 at a predetermined cycle.

First, in step S200, an abnormality occurs in the pump control unit 20 of the drainage pump device 2 depending on whether the soundness determination unit 301 has received the soundness signal from the drainage pump device 2 according to the soundness transmission condition. determine whether or not

When it is determined that an abnormality has occurred in the pump control unit 20 as the determination result of step S200 (step S201: Yes), in step S210, the weather information acquisition unit 300 selects the pump control unit 20 in which the abnormality has occurred. The weather information of the monitored location of the provided drainage pump device 2 is acquired from the weather information providing device 7 .

Next, in step S220, the first pump control unit abnormality processing unit 302 performs drainage work on the drainage pump device 2 having the pump control unit 20 in which the abnormality has occurred, based on the weather information of the monitoring location acquired in step S210. Outputs support request information requesting support for

Next, in step S230, the second pump control unit abnormality processing unit 303, based on the weather information of the monitored location acquired in step S210, the pump unit of the drainage pump device 2 including the pump control unit 20 in which the abnormality has occurred. 25 is transmitted to the pump unit 25 to instruct the operation of the pump. When the pump unit 25 receives the pump operation signal without going through the pump control unit 20, the operation of the pump unit 25 is forcibly started. In the series of processes (drainage pump management method) shown in FIG. This corresponds to the control unit abnormality processing step.

As described above, according to the management device 3 according to the present embodiment, the management control unit 30 determines whether an abnormality has occurred in the pump control unit 20 according to the state of reception of the soundness signal from the drainage pump device 2. is determined, and if it is determined that an abnormality has occurred in the pump control unit 20, based on the weather information, support request information for the drainage pump device 2 including the pump control unit 20 is output, or the pump is sent to the pump unit 25 to send driving signals. Therefore, even if an abnormality occurs in the pump control unit 20, it is possible to reduce flood damage to the monitoring location.

(Second embodiment)
FIG. 7 is an overall configuration diagram showing an example of a drainage pump management system 1a according to the second embodiment. A drainage pump management system 1a according to the second embodiment differs from the first embodiment in that a learning model used for creating a drainage work support plan for a management area in which a plurality of drainage pump devices 2 are arranged is 12, and a management device 3a functioning as a drainage pump support plan creation device that creates a drainage work support plan using the learning model 12 generated by the machine learning device 8. do. The basic configuration and operation are
Since it is the same as the first embodiment, the differences from the first embodiment will be mainly described below.

The machine learning device 8 operates as the main body of the learning phase of machine learning, and uses the learning data 11 to generate the learning model 12 by machine learning. The trained learning model 12 is provided to the management device 3a via the network 10, a recording medium, or the like.

The management device 3a operates as the subject of the machine learning inference phase, and uses the learning model 12 generated by the machine learning device 8 to create support plan information that defines the support plan for the drainage work,
For example, it outputs (transmits) to the administrator terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the like.

The support plan information is a support plan for the drainage work by at least one of the drainage pump vehicle 5 and the worker 101, assuming a situation where the drainage capacity of the drainage pump device 2a alone cannot drain the water accumulated in the monitoring location in a timely manner. It is determined. The support plan information includes support priority information indicating the priority of the drainage pump device 2a that requires support for the drainage work, and support arrangement indicating the arrangement status of at least one of the drainage pump vehicle 5 and the worker 101 in the management area. At least one of information is included.

The support priority information is set as a priority, for example, like the numbers (1 to 5) in the frame shown in FIG. Alternatively, it may be set higher as the speed at which the water level rises at the monitored location is higher, or it may be set based on a comprehensive judgment of these factors. The support placement information is stored in the management area, for example,
This is an arrangement situation when the drainage pump vehicle 5 and the worker 101 are on standby, respectively. , the destination positions of the drain pump vehicle 5 and the worker 101 (marked with "x" in FIG. 7) are specified.

(Drain pump device 2a)
FIG. 8 is a block diagram showing an example of a drainage pump device 2a according to the second embodiment.

By executing the drainage pump control program 211a stored in the storage unit 21, the pump control unit 20 controls the pump operation processing unit 200, the weather information acquisition unit 201, the abnormality determination unit 202.
, water level detector abnormality processing unit 203, pump unit abnormality processing unit 204, soundness signal transmission processing unit 20
5 and a water level signal transmission processing unit 206 .

The water level signal transmission processing unit 206 transmits a water level signal indicating the water level detected by the water level detection unit 24 to the management device 3a via the communication unit 22 and the network 10 according to predetermined water level transmission conditions. The water level transmission condition defines a condition for transmitting a water level signal, for example, a predetermined transmission period or transmission time. The water level transmission condition may be the same as the soundness transmission condition, in which case the water level signal may function as the soundness signal.

(Machine learning device 8)
FIG. 9 is a block diagram showing an example of the machine learning device 8 according to the second embodiment. The machine learning device 8 is composed of a general-purpose or dedicated computer 900 (see FIG. 4), like other devices.

The machine learning device 8 includes a control unit 80 composed of a processor or the like, a storage unit 81 composed of an HDD, an SSD, a memory, etc., a communication unit 82 serving as a communication interface with the network 10, a keyboard, a mouse, and the like. and an input unit 83 configured by a display or the like. Note that the input unit 83 and the display unit 84 may be omitted.

The storage unit 81 stores the learning data 11, the learning model 12, and the machine learning program 810.
and stores an operating system, other programs, various data, and the like. The storage unit 81 functions as a learning data storage unit that stores the learning data 11 and a trained model storage unit that stores the learning model 12 .

The control unit 80 functions as a learning data acquisition unit 800 and a machine learning unit 801 by executing a machine learning program 810 stored in the storage unit 81 .

The learning data acquisition unit 800 is connected to another device via the communication unit 82 and the network 10, and acquires learning data 11 composed of region data as input data and support plan information as output data. Acquired and stored in the storage unit 81 . The learning data 11 is data used as teacher data (training data), verification data, and test data in supervised learning. Further, the support plan information is data used as correct labels in supervised learning.

The machine learning unit 801 performs machine learning using multiple sets of learning data 11 stored in the storage unit 81 . That is, the machine learning unit 801 inputs a plurality of sets of learning data 11 to the learning model 12, and causes the learning model 12 to learn the correlation between the area data and the support plan information included in the learning data 11. A completed learning model 12 (specifically, an adjusted weight parameter group) is generated and stored in the storage unit 81 .

Note that the number of learning models 12 generated by the machine learning unit 801 and stored in the storage unit 81 is not limited to one. A plurality of learning models 12 with different conditions, such as the type of data included, may be stored. In that case, the learning data acquisition unit 800 acquires a plurality of types of learning data 11 each having a data structure corresponding to a plurality of learning models 12 with different conditions and stores them in the storage unit 81 .

FIG. 10 is a diagram showing an example of the learning model 12 and the learning data 11. As shown in FIG. Learning model 1
The learning data 11 used in the machine learning of 2 consists of area data and support plan information.

The area data constituting the learning data 11 includes weather information in the learning area corresponding to the management area, location information of at least one of the drainage pump vehicle 5 and the worker 101 located in the learning area, and time transition of the water level at the monitoring point. and geographic information of monitoring points within the learning area. The learning area may be the same area as the management area, or may be an area different from the management area.

Meteorological information is a record of rainfall, weather, etc. for each area divided into meshes.
For example, it includes current weather data at a predetermined reference time, and weather forecast data at a future time after a predetermined time from the reference time (for example, one hour, two hours, etc.).

The position information is information indicating the current positions of the drainage pump vehicle 5 and the worker 101 at the reference time.

The water level transition information is information indicating the temporal transition of the water level at the monitoring point in each drainage pump device 2a. , 2 hours ago, etc.).

The geographic information is positional coordinates (latitude, longitude, altitude) of monitoring points in each drainage pump device 2a.
is information indicating The geographic information may include positional coordinates of rainwater pipes, sewage pipes, rivers, and the like.

The support plan information constituting the learning data 11 includes support priority information indicating the priority of the drain pump device 2a that requires support for the drain work, and at least one of the drain pump vehicle 5 and the worker 101 for the management area. at least one of the support placement information indicating the placement status of the

The learning data acquisition unit 800 may acquire, as the learning data 11, actual past situations recorded for each of the above information, or virtual situations assumed by the administrator 100 may be, for example, , data input from the administrator terminal device 4 may be acquired as the learning data 11, or data obtained by simulating the water level at the monitoring location and the placement of the drainage pump vehicle 5 and the worker 101 may be acquired as the learning data 11. Alternatively, the learning data 11 may be obtained by combining these.

The learning model 12 employs, for example, a neural network structure, and includes an input layer 120 , an intermediate layer 121 and an output layer 122 . A synapse (not shown) connecting each neuron is provided between each layer, and a weight is associated with each synapse. A set of weight parameters consisting of the weight of each synapse is adjusted by machine learning. The input layer 120 has a number of neurons corresponding to region data as input data, and each value of region data is input to each neuron. The output layer 122 has a number of neurons corresponding to the support plan information as output data, and outputs prediction results (inference results) of the support plan information for the area data as output data.

In this embodiment, the learning model 12 and the learning data 11 will be described as having a data configuration as shown in FIG. 12 and the data structure of the learning data 11 may be changed as appropriate.

(Management device 3a)
FIG. 11 is a block diagram showing an example of a management device 3a according to the second embodiment. Figure 12
[Fig. 10] is a functional explanatory diagram showing an example of a management device 3a according to the second embodiment.

The storage unit 31 includes a drainage pump management database 310 and a drainage pump management program 311.
, the drainage pump support plan creation program 312, and the learning model 12, as well as the operating system, other programs, various data, and the like. Storage unit 31
functions as a learned model storage unit that stores the learned model 12 that has been learned.

By executing the drainage pump management program 311 stored in the storage unit 31, the management control unit 30 performs a weather information acquisition unit 300, a soundness determination unit 301, a first pump control unit abnormality processing unit 302, and a 2 function as the pump control unit abnormality processing unit 303, and by executing the drainage pump support plan creation program 312 stored in the storage unit 31, the data acquisition unit 304, the support plan creation unit 305, and the output processing unit 306. The drainage pump management program 311 and the drainage pump support plan creation program 312 are
It may be realized by one program.

The data acquisition unit 304 is connected to other devices via the communication unit 32 and the network 10, and is configured to obtain weather information of the management area, location information of at least one of the drainage pump vehicle 5 and the worker 101 located in the management area, water level, and so on. area data including at least water level transition information indicating the time transition of , and geographic information of monitoring points within the management area.

The weather information of the management area is acquired by the data acquisition unit 304 by receiving it from the weather information providing device 7, for example. The position information of the drainage pump vehicle 5 and the worker 101 is obtained from the detection result of the current position detection unit provided in the drainage pump vehicle 5 and the current position detection unit provided in the worker terminal device 6 possessed by the worker 101. is obtained by the data obtaining unit 304 by receiving the detection results from the drainage pump vehicle 5 and the worker 101 respectively. The water level transition information is acquired by the data acquisition unit 304 as information based on the water level signal by receiving the water level signal from the drainage pump device 2a according to the water level transmission conditions. The geographic information of the monitored location is acquired by the data acquisition unit 304 by referring to the drainage pump management database 310 .

The support plan creation unit 305 inputs the area data acquired by the data acquisition unit 304 to the trained learning model 12 stored in the storage unit 31, thereby creating support plan information for the area data.

Note that the number of learning models 12 stored in the storage unit 31 is not limited to one. , a plurality of learning models 12 with different conditions may be stored and selectively available. In addition, the learning model 12 may be stored in a storage unit of an external computer (for example, a server computer or a cloud computer). In that case, the support plan creation unit 305 accesses the external computer good.

The output processing unit 306 performs output processing for outputting the support plan information generated by the support plan creation unit 305 . For example, the output processing unit 306 transmits the support plan information to, for example, the manager terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, etc., so that the display screen based on the support plan information is displayed by the manager. It is displayed on the terminal device 4, the drainage pump vehicle 5, the worker terminal device 6, and the like.

(machine learning method)
FIG. 13 is a flow chart showing an example of the operation of the machine learning device 8 according to the second embodiment. The series of processes shown in FIG. 13 is executed by the machine learning device 8, for example, when an administrator's operation requesting creation of the learning model 12 is accepted via the administrator terminal device 4. FIG.

First, in step S300, the learning data acquisition unit 800 acquires a desired number of learning data 11 as preparation for starting machine learning, and stores the acquired learning data 11 in the storage unit 81. do. The number of learning data 11 prepared here may be set in consideration of the inference accuracy required for the finally obtained learning model 12 .

Next, in step S310, the machine learning unit 801 prepares the learning model 12 before learning to start machine learning. The pre-learning learning model 12 prepared here is composed of the neural network model illustrated in FIG. 10, and the weight of each synapse is set to an initial value.

Next, in step S320, the machine learning unit 801 randomly acquires one set of learning data 11 from the multiple sets of learning data 11 stored in the storage unit 81, for example.

Next, in step S330, the machine learning unit 801 converts the region data (input data) included in the set of learning data 11 into the prepared learning model 12 before learning (or during learning).
input to the input layer 120 of . As a result, support plan information (output data) is output as an inference result from the output layer 122 of the learning model 12, but the output data is generated by the learning model 12 before learning (or during learning). . Therefore, in the pre-learning (or during learning) state, the output data output as the inference result indicates information different from the support plan information (correct label) included in the learning data 11 .

Next, in step S340, the machine learning unit 801 determines the support plan information (correct label) included in the set of learning data 11 acquired in step S320, and
Support plan information (output data) output as an inference result from the output layer 122 in 330
and perform processing (back-progression) to adjust the weight of each synapse, thereby performing machine learning. Thereby, the machine learning unit 801 causes the learning model 12 to learn the correlation between the area data and the support plan information.

Next, in step S350, the machine learning unit 801 determines whether or not a predetermined learning end condition is satisfied, for example, the support plan information (correct label) included in the learning data 11 and output as the inference result. It is determined based on the evaluation value of the error function based on the support plan information (output data) and the remaining number of unlearned learning data 11 stored in the storage unit 81 .

In step S350, the machine learning unit 801 determines that the learning end condition is not satisfied,
If it is determined to continue the machine learning (No in step S350), the process returns to step S320, and the steps S320 to S340 are performed multiple times on the learning model 12 being learned using the unlearned learning data 11. . On the other hand, in step S350, the machine learning unit 8
01 determines that the learning termination condition is satisfied and the machine learning is terminated (step S3
50: Yes), the process proceeds to step S360.

Then, in step S360, the machine learning unit 801 stores in the storage unit 81 the learned learning model 12 (adjusted weight parameter group) generated by adjusting the weight associated with each synapse. In the series of processes (machine learning method) shown in FIG. 13, step S300 is a learning data storage step, steps S310 to S350 are machine learning steps,
Step S360 corresponds to the learned model storage step.

As described above, according to the machine learning device 8 according to the present embodiment, it is possible to provide the learning model 12 capable of creating (inferring) the support plan information for the area data from the area data.

(How to create a drainage pump support plan)
FIG. 14 is a flow chart showing an example of the operation of the management device 3a according to the second embodiment. An operation example in which the management device 3a creates a support plan at a specific time when a predetermined support plan creation condition is satisfied will be described below. The support plan creation condition may be determined by a predetermined creation cycle or creation time, or may be determined by weather conditions, or a creation request from the administrator terminal device 4 based on the operation of the administrator is accepted. Even when

First, in step S400, when a predetermined support plan creation condition is satisfied, the data acquisition unit 304 of the management device 3a obtains the weather information of the management area, the location information of the drainage pump vehicle 5 and the worker 101, and the water level transition of the monitored location. Information and area data including at least geographic information of the monitored location is obtained.

Next, in step S410, the support plan creation unit 305 inputs the area data acquired in step S400 to the learning model 12 as input data, thereby creating support plan information for the area data.

Next, in step S420, the output processing unit 306 transmits the support plan information to the administrator terminal device 4 as output processing for outputting the support plan information created in step S410. Then, the manager terminal device 4 displays a display screen based on the support plan information, so that the support plan can be confirmed by the manager. In addition to or instead of the administrator terminal device 4, the destination of the support plan information may be the drainage pump truck 5 and the worker terminal device 6. FIG. In the series of processes (drain pump support plan creating method) shown in FIG. 14, step S400
corresponds to the data acquisition step, step S410 corresponds to the support plan creation step, and step S420 corresponds to the output processing step.

As described above, according to the management device 3a (drainage pump support plan creation device) according to the present embodiment, by inputting region data into the learning model 12, support plan information for the region data is created. The drainage work by the pump truck 5 and the worker 101 can be properly carried out.

(Other embodiments)
The present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the gist of the present invention. All of them are included in the technical idea of the present invention.

In the above embodiments, the management devices 3 and 3a, the administrator terminal device 4, and the machine learning device 8 are described as being composed of separate devices, but these three devices are composed of a single device. Alternatively, any two of the three devices may be configured as a single device. Further, in the above embodiment, a case has been described in which the management device 3a functions as a drainage pump support plan creation device, but the drainage pump support plan creation device may be configured by a device other than the management device 3a. . In that case, the drainage pump support plan creation device should include at least the data acquisition unit 304 and the support plan creation unit 305 .

In the above embodiment, each device of the drainage pump management system 1, 1a is shown in FIGS.
and the case of operating according to the flowchart shown in FIG. 14, the execution order of each step may be changed as appropriate, and some steps may be omitted. For example, step S110 in FIG. 5 may be executed immediately before steps S130 and S140, steps S220 and S230 in FIG. 6 may be changed in execution order, or one of them may be omitted.

In the above embodiment, a case where a neural network is adopted as a learning model for realizing machine learning by the machine learning unit 801 has been described, but other machine learning models may be adopted. Other machine learning models include, for example, tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, recurrent neural networks, convolutional neural networks, and neural network types such as LSTM (including deep learning ), hierarchical clustering, non-hierarchical clustering, k-nearest neighbor method, k-means method and other clustering types, principal component analysis, factor analysis, logistic regression and other multivariate analyzes, and support vector machines. Further, machine learning by the machine learning unit 801 may be realized by reinforcement learning.

(Inference Apparatus, Inference Method and Inference Program)
The present invention is not only based on the aspect of the drainage pump support plan creation device (drainage pump support plan creation method or drainage pump support plan creation program) according to the above embodiment, but also an inference device used to infer support plan information. It can also be provided in the form of (inference method or inference program). In that case, the inference device (inference method or inference program) may include a memory and a processor, and the processor of these may execute a series of processes. The series of processes includes a data acquisition process (data acquisition process) for acquiring area data, and an inference process (inference process) for inferring support plan information for the area data once the area data is acquired in the data acquisition process. including.

By providing it in the form of an inference device (inference method or inference program), it becomes possible to apply it to various devices more easily than when implementing a drainage pump support plan creation device. inference device (
Inference method or inference program) infers support plan information, using the learned learning model generated by the machine learning device and machine learning method according to the above embodiment, the inference method implemented by the support plan creation unit It can be naturally understood by those skilled in the art that it may be applied.

1, 1a... drainage pump management system, 2, 2a... drainage pump device, 3, 3a... management device,
4... Administrator terminal device, 5... Drainage pump vehicle, 6... Worker terminal device,
7 weather information providing device, 8 machine learning device, 10 network,
11... Learning data, 12... Learning model,
20... pump control section, 21... storage section, 22... communication section, 24... operation display section,
25... Water level detection unit, 26... Pump unit,
30... Management control unit, 31... Storage unit, 32... Communication unit, 33... Input unit, 34... Display unit,
80... control unit, 81... storage unit, 82... communication unit, 83... input unit, 84... display unit,
DESCRIPTION OF SYMBOLS 100...Administrator 101...Worker 120...Input layer 121...Intermediate layer 122...Output layer 200...Pump operation processing part 201...Weather information acquisition part 202...Abnormality determination part
203 ... water level detection unit abnormality processing unit, 204 ... pump unit abnormality processing unit,
205 ... soundness signal transmission processing unit, 206 ... water level signal transmission processing unit,
210 ... Drainage pump setting data, 211 ... Drainage pump control program,
300 ... weather information acquisition unit, 301 ... soundness determination unit,
302... first pump control unit abnormality processing unit, 303... second pump control unit abnormality processing unit,
304 ... data acquisition unit, 305 ... support plan creation unit, 306 ... output processing unit,
310... drainage pump management database, 311... drainage pump management program,
312 ... Drainage pump support plan creation program,
800... Learning data acquisition unit, 801... Machine learning unit, 810... Machine learning program,
900 computer

Claims (12)

a water level detection unit that detects the water level at the monitoring location;
a pump unit for draining water accumulated in the monitoring location;
A drainage pump device comprising: a pump control section that controls operation of the pump section based on the water level detected by the water level detection section,
The pump control unit
a weather information acquisition unit that acquires weather information of the monitoring location;
an abnormality determination unit that determines whether an abnormality has occurred in the water level detection unit or the pump unit;
a water level detection unit abnormality processing unit that controls the operation of the pump unit based on the weather information when it is determined that an abnormality has occurred in the water level detection unit;
When it is determined that an abnormality has occurred in the pump unit, at least one of the water level detected by the water level detection unit and the weather information is used to request support for drainage work by at least one of a drainage pump vehicle and a worker. a pump unit abnormality processing unit that outputs support request information to
Drainage pump device. one or more drainage pump devices according to claim 1;
A drainage pump management system comprising a management device communicable with the drainage pump device,
The pump control unit
a health signal transmission processing unit that transmits a health signal indicating the health of the drainage pump device to the management device according to a predetermined health transmission condition;
The management device
a weather information acquisition unit that acquires weather information of the monitoring location;
a soundness determination unit that determines whether or not an abnormality has occurred in the pump control unit of the drainage pump device according to whether or not the soundness signal has been received from the drainage pump device according to the soundness transmission condition; ,
a first method for outputting the support request information for requesting the drainage pump device including the pump control unit to support the drainage work based on the weather information when it is determined that an abnormality has occurred in the pump control unit; a pump control unit abnormality processing unit;
Drainage pump management system. The pump section
configured to be able to receive a pump operation signal instructing the operation of the pump unit from the management device without going through the pump control unit;
The management device
When it is determined that an abnormality has occurred in the pump control unit, the pump operation signal for instructing the operation of the pump unit of the drainage pump device including the pump control unit is transmitted to the pump unit based on the weather information. a second pump control unit abnormality processing unit that
The drainage pump management system according to claim 2. The pump control unit
A water level signal transmission processing unit that transmits a water level signal indicating the water level detected by the water level detection unit to the management device according to a predetermined water level transmission condition,
The management device
Weather information of a management area in which a plurality of the drainage pump devices are arranged, location information of at least one of the drainage pump vehicle and the worker located in the management region, received from the drainage pump device according to the water level transmission condition a data acquisition unit that acquires area data including at least water level transition information, which is information based on the water level signal and indicates the temporal transition of the water level, and geographic information of the monitoring location within the management area;
area data including at least the weather information, the location information, the water level transition information, and the geographic information in the learning area corresponding to the management area; and support plan information defining a support plan for the drainage work for the learning area. a support plan creation unit that creates the support plan information for the region data by inputting the region data acquired by the data acquisition unit into a learning model that has learned the correlation of ,
The drainage pump management system according to claim 2 or 3. The support plan information is
including at least assistance priority information indicating the priority of the drainage pump device that requires assistance for the drainage work;
The drainage pump management system according to claim 4. The support plan information is
including at least support arrangement information indicating the arrangement status of at least one of the drainage pump vehicle and the worker with respect to the management area;
The drainage pump management system according to claim 4. A drainage pump support plan creation device for creating a drainage work support plan for at least one of a drainage pump vehicle and a worker for a management area in which a plurality of drainage pump devices for controlling the operation of the pump unit based on the water level at the monitoring point is arranged. There is
Weather information of the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the monitoring within the management area a data acquisition unit that acquires area data that includes at least geographic information of a location;
area data including at least the weather information, the location information, the water level transition information, and the geographic information in the learning area corresponding to the management area; and support plan information defining a support plan for the drainage work for the learning area. a support plan creation unit that creates the support plan information for the region data by inputting the region data acquired by the data acquisition unit into a learning model that has learned the correlation of ,
Drainage pump support planning device. A reasoning device used to create a support plan for drainage work by at least one of a drainage pump vehicle and a worker for a management area in which a plurality of drainage pump devices that control the operation of the pump unit based on the water level at the monitoring point are arranged. There is
The reasoning device comprises a memory and a processor,
The processor
Weather information of the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the monitoring within the management area a data acquisition process for acquiring area data including at least geographic information of a location;
an inference process for inferring support plan information that defines a support plan for the drainage work for the area data when the area data is obtained in the data acquisition process;
reasoning device. A learning model used to create a support plan for drainage work by at least one of a drainage pump vehicle and a worker for a management area in which a plurality of drainage pump devices that control the operation of the pump unit based on the water level at the monitoring point are arranged. A machine learning device that generates
Weather information in a learning area corresponding to the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the management area a learning data storage unit for storing a plurality of sets of learning data composed of area data including at least the geographical information of the monitoring point in the learning area and support plan information defining a support plan for the drainage work for the learning area; ,
a machine learning unit that causes the learning model to learn the correlation between the area data and the support plan information by inputting a plurality of sets of the learning data into the learning model;
a learned model storage unit that stores the learning model for which the correlation has been learned by the machine learning unit;
Machine learning device. A drainage pump support plan creation method for creating a drainage work support plan by at least one of a drainage pump vehicle and a worker for a management area in which a plurality of drainage pump devices for controlling the operation of the pump unit based on the water level at the monitoring point is arranged There is
Weather information of the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the monitoring within the management area a data acquisition step of acquiring area data including at least geographic information of a location;
area data including at least the weather information, the location information, the water level transition information, and the geographic information in the learning area corresponding to the management area; and support plan information defining a support plan for the drainage work for the learning area. and a support plan creation step of creating the support plan information for the region data by inputting the region data acquired in the data acquisition step into a learning model in which the correlation of is learned by machine learning. ,
How to create a drainage pump support plan. A reasoning method used to create a support plan for drainage work by at least one of a drainage pump vehicle and a worker in a management area where multiple drainage pump devices that control the operation of the pump unit based on the water level at the monitoring point are arranged. There is
Weather information of the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the monitoring within the management area a data acquisition step of acquiring area data including at least geographic information of a location;
an inference step of inferring support plan information that defines a support plan for the drainage work for the region data when the region data is obtained in the data obtaining step;
reasoning method. A learning model used to create a support plan for drainage work by at least one of a drainage pump vehicle and a worker for a management area in which a plurality of drainage pump devices that control the operation of the pump unit based on the water level at the monitoring point are arranged. A machine learning method for generating,
Weather information in a learning area corresponding to the management area, location information of at least one of the drainage pump vehicle and the worker located in the management area, water level transition information indicating the time transition of the water level, and the management area a plurality of sets of learning data including area data including at least the geographical information of the monitoring point in the area and support plan information defining a support plan for the drainage work for the learning area are stored in the learning data storage unit. a training data storage step;
a machine learning step of causing the learning model to learn the correlation between the region data and the support plan information by inputting a plurality of sets of the learning data into the learning model;
a learned model storage step of storing the learning model, the correlation of which has been learned by the machine learning step, in a learned model storage unit;
machine learning method.

Images